中文
相关论文

相关论文: A Survey of Methods to Leverage Monolingual Data i…

200 篇论文

Neural machine translation~(NMT) is ineffective for zero-resource languages. Recent works exploring the possibility of unsupervised neural machine translation (UNMT) with only monolingual data can achieve promising results. However, there…

计算与语言 · 计算机科学 2021-04-02 Mingxuan Wang , Hongxiao Bai , Hai Zhao , Lei Li

Multi-source translation systems translate from multiple languages to a single target language. By using information from these multiple sources, these systems achieve large gains in accuracy. To train these systems, it is necessary to have…

计算与语言 · 计算机科学 2018-11-09 Yuta Nishimura , Katsuhito Sudoh , Graham Neubig , Satoshi Nakamura

Multilingual machine translation has recently been in vogue given its potential for improving machine translation performance for low-resource languages via transfer learning. Empirical examinations demonstrating the success of existing…

计算与语言 · 计算机科学 2020-05-13 Ion Madrazo Azpiazu , Maria Soledad Pera

Transfer learning from a high-resource language pair `parent' has been proven to be an effective way to improve neural machine translation quality for low-resource language pairs `children.' However, previous approaches build a custom…

计算与语言 · 计算机科学 2019-09-23 Mozhdeh Gheini , Jonathan May

Recently proposed data collection frameworks for endangered language documentation aim not only to collect speech in the language of interest, but also to collect translations into a high-resource language that will render the collected…

计算与语言 · 计算机科学 2018-06-12 Antonis Anastasopoulos , David Chiang

We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in the recent years. MNMT has been useful in improving translation quality as a result of knowledge transfer. MNMT is more promising…

计算与语言 · 计算机科学 2020-01-08 Raj Dabre , Chenhui Chu , Anoop Kunchukuttan

Machine translation has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale parallel corpora. There have been numerous attempts to extend these successes to low-resource…

计算与语言 · 计算机科学 2018-04-16 Guillaume Lample , Alexis Conneau , Ludovic Denoyer , Marc'Aurelio Ranzato

Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However,…

计算与语言 · 计算机科学 2017-05-02 Meng Fang , Trevor Cohn

We propose a method of curating high-quality comparable training data for low-resource languages with monolingual annotators. Our method involves using a carefully selected set of images as a pivot between the source and target languages by…

计算与语言 · 计算机科学 2020-04-30 Aman Madaan , Shruti Rijhwani , Antonios Anastasopoulos , Yiming Yang , Graham Neubig

Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zeroshot) translation directions not observed at training time. We…

计算与语言 · 计算机科学 2018-11-06 Surafel M. Lakew , Quintino F. Lotito , Matteo Negri , Marco Turchi , Marcello Federico

While neural machine translation (NMT) has become the new paradigm, the parameter optimization requires large-scale parallel data which is scarce in many domains and language pairs. In this paper, we address a new translation scenario in…

计算与语言 · 计算机科学 2017-11-06 Yining Wang , Yang Zhao , Jiajun Zhang , Chengqing Zong , Zhengshan Xue

Multilingual neural machine translation (NMT) has recently been investigated from different aspects (e.g., pivot translation, zero-shot translation, fine-tuning, or training from scratch) and in different settings (e.g., rich resource and…

计算与语言 · 计算机科学 2019-12-30 Xu Tan , Yichong Leng , Jiale Chen , Yi Ren , Tao Qin , Tie-Yan Liu

Translation to or from low-resource languages LRLs poses challenges for machine translation in terms of both adequacy and fluency. Data augmentation utilizing large amounts of monolingual data is regarded as an effective way to alleviate…

计算与语言 · 计算机科学 2019-06-11 Mengzhou Xia , Xiang Kong , Antonios Anastasopoulos , Graham Neubig

The scarcity of large parallel corpora is an important obstacle for neural machine translation. A common solution is to exploit the knowledge of language models (LM) trained on abundant monolingual data. In this work, we propose a novel…

计算与语言 · 计算机科学 2020-10-27 Christos Baziotis , Barry Haddow , Alexandra Birch

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

计算与语言 · 计算机科学 2023-04-04 Viet H. Pham , Thang M. Pham , Giang Nguyen , Long Nguyen , Dien Dinh

We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of…

计算与语言 · 计算机科学 2016-01-07 Orhan Firat , Kyunghyun Cho , Yoshua Bengio

Multilingual models have been widely used for cross-lingual transfer to low-resource languages. However, the performance on these languages is hindered by their underrepresentation in the pretraining data. To alleviate this problem, we…

计算与语言 · 计算机科学 2023-05-29 Tomasz Limisiewicz , Dan Malkin , Gabriel Stanovsky

The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language. Thus, the majority of the world's languages cannot benefit from recent progress in NLP…

计算与语言 · 计算机科学 2022-04-07 Xinyi Wang , Sebastian Ruder , Graham Neubig

Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a…

计算与语言 · 计算机科学 2019-06-06 Yunsu Kim , Yingbo Gao , Hermann Ney

Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper, we propose two simple…

计算与语言 · 计算机科学 2021-03-15 Gaurav Kumar , Philipp Koehn , Sanjeev Khudanpur